水资源保护2025，Vol.41Issue(5)：106-114,131,10.DOI:10.3880/j.issn.1004-6933.2025.05.012
基于误差校正融合模型的自适应带宽洪水区间预报
Adaptive bandwidth flood interval forecasting based on error-corrected hybrid model
摘要
Abstract
To address the issues of complex flood generation and concentration processes,sudden flood occurrence,and low prediction accuracy of physical mechanism models in small watersheds,two kinds of hybrid methods,namely the error-corrected hybrid models mainly based on physical mechanism models and the mechanism-guided hybrid model mainly based on deep learning models were constructed by using the HYMOD,GR4J,and LSTM models.The simulation performance of different hybrid methods was explored,and the adaptive bandwidth kernel density estimation(ABKDE)was also proposed for flood interval forecasting with different lead times.With the typical small watershed of the Heihe River in Shaanxi Province as an example,the flood forecasting performance of each model was evaluated.The results show that the single models,including the HYMOD,GR4J,and LSTM models can provide reliable forecast results,and the deep learning model LSTM is superior to the physical mechanism models HYMOD and GR4J,while the simulation performance of the HYMOD model is more stable than that of the GR4J model.The hybrid models not only retain the interpretability of the physical model,but also improve the accuracy of flood forecasting,with the Nash efficiency coefficient increasing by 3.66％to 70.51％,demonstrating a significant improvement in forecasting performance compared to the single models.The error-corrected hybrid models have better forecasting performance than the mechanism-guided hybrid models,among which the error-corrected hybrid model HYMOD-LSTM has the best forecasting effect.The prediction interval coverage probability of the HYMOD-LSTM model at the 90％confidence level exceeds 92％,demonstrating excellent performance of the model.The HYMOD-LSTM model can effectively reflect the uncertainty of the forecasted flood process,and the results of flood interval forecasting based on ABKDE are reasonable and reliable,reflecting the good adaptive adjustment ability of ABKDE.关键词
洪水预报/误差校正融合模型/机理引导融合模型/自适应带宽核密度估计/黑河流域Key words
flood forecasting/error-corrected hybrid model/mechanism-guided hybrid model/adaptive bandwidth kernel density estimation/the Heihe River Basin分类
天文与地球科学引用本文复制引用
康艳,艾慧茹,彭仁娟,胡维贺,吴巍然,张梓尚,由宇军..基于误差校正融合模型的自适应带宽洪水区间预报[J].水资源保护,2025,41(5):106-114,131,10.基金项目
国家自然科学基金面上项目(52579022,52379026) （52579022,52379026）
内蒙古自治区水利科技专项(202501010505A) （202501010505A）
中国水利水电科学研究院内蒙古阴山北麓草原生态水文国家野外科学观测研究站开放基金项目(YSS202508) （YSS202508）
陕西省水利科技项目(2019slkj-14) （2019slkj-14）
